[英]PyTorch matrix factorization embedding error
I'm trying to use a single hidden layer NN to perform matrix factorization.我正在尝试使用单个隐藏层 NN 来执行矩阵分解。 In general, I'm trying to solve for a tensor, V, with dimensions [9724x300] where there are 9724 items in inventory, and 300 is the arbitrary number of latent features.
一般来说,我试图求解一个尺寸为 [9724x300] 的张量 V,其中库存中有 9724 个项目,而 300 是任意数量的潜在特征。
The data that I have is a [9724x9724] matrix, X, where columns and rows represent the number of mutual likes.我拥有的数据是一个 [9724x9724] 矩阵 X,其中的列和行代表相互喜欢的数量。 (eg X[0,1] represents the sum of users who like both item 0 and item 1. Diagonal entries are not of importance.
(例如,X[0,1] 表示同时喜欢项目 0 和项目 1 的用户的总和。对角线条目并不重要。
My goal is to use MSE loss, such that the dot product of V[i,:] on V[j,:] transposed is very, very close to X[i,j].我的目标是使用 MSE 损失,使得 V[i,:] 在 V[j,:] 转置后的点积非常非常接近 X[i,j]。
Below is code that I've adapted from the below link.以下是我从以下链接改编的代码。
https://blog.fastforwardlabs.com/2018/04/10/pytorch-for-recommenders-101.html https://blog.fastforwardlabs.com/2018/04/10/pytorch-for-recommenders-101.html
import torch
from torch.autograd import Variable
class MatrixFactorization(torch.nn.Module):
def __init__(self, n_items=len(movie_ids), n_factors=300):
super().__init__()
self.vectors = nn.Embedding(n_items, n_factors,sparse=True)
def forward(self, i,j):
return (self.vectors([i])*torch.transpose(self.vectors([j]))).sum(1)
def predict(self, i, j):
return self.forward(i, j)
model = MatrixFactorization(n_items=len(movie_ids),n_factors=300)
loss_fn = nn.MSELoss()
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)
for i in range(len(movie_ids)):
for j in range(len(movie_ids)):
# get user, item and rating data
rating = Variable(torch.FloatTensor([Xij[i, j]]))
# predict
# i = Variable(torch.LongTensor([int(i)]))
# j = Variable(torch.LongTensor([int(j)]))
prediction = model(i, j)
loss = loss_fn(prediction, rating)
# backpropagate
loss.backward()
# update weights
optimizer.step()
The error returned is:返回的错误是:
TypeError: embedding(): argument 'indices' (position 2) must be Tensor, not list
I'm very new to embeddings.我对嵌入很陌生。 I had tried replacing embeddings as a simple float tensor, however the MatrixFactorization class, which I defined, did not recognize the tensor as a model parameters to be optimized over.
我曾尝试将嵌入替换为简单的浮点张量,但是我定义的 MatrixFactorization class 没有将张量识别为要优化的 model 参数。
Any thoughts on where I'm going wrong?关于我要去哪里错的任何想法?
You are passing a list to self.vectors
,您正在将列表传递给
self.vectors
,
return (self.vectors([i])*torch.transpose(self.vectors([j]))).sum(1)
Try to convert it to tensor before you call self.vectors()
在调用
self.vectors()
之前尝试将其转换为张量
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.